Skip to main content

ā€‹
Video Tutorial

Agent Node is the core building block of every Dograh workflow. It holds the LLM prompt that drives the conversation, any tools the agent can call, and knowledge base documents to reference. You can have multiple Agent Nodes in a single workflow, each handling a distinct phase of the conversation. The Edges connected with Agent Nodes are pathways that the LLMs can take depending on how the conversation has been going so far.

ā€‹
What goes in an Agent Node

Prompt The instructions for how the agent should behave at this step. Be explicit about sequence: if the agent should confirm identity before discussing payment, say so in the prompt. Vague prompts produce inconsistent behavior. Tools External functions the agent can call during this step - for example, looking up account balances or updating a CRM record. Add tools via the ā€œHTTP & Toolsā€ or ā€œMCPā€ tabs in the node settings panel. Allow Interruption When on, the caller can interrupt the agent mid-utterance. Add Global Prompt When on and a Global Node exists, the Global Prompt is prepended to this nodeā€™s Prompt at runtime. On by default. Knowledge Base Documents Files the agent can reference when answering questions - product guides, FAQs, policies. Attach them via the ā€œManage Documentsā€ button in the node settings panel.

ā€‹
Configuring edges

Each outgoing edge has a condition written in plain language. The LLM evaluates the conversation and picks the edge whose condition best matches. Write edge conditions as specifically as possible:
If the agent keeps routing to the wrong edge, make the condition more specific. Conditions like ā€œuser respondsā€ or ā€œconversation endsā€ are too broad and will route unpredictably.

ā€‹
Extracting variables

Agent Node can extract structured data from the conversation after the node completes. Enable this in the node settings under ā€œEnable Variable Extraction.ā€ Once enabled, configure two things:
  • Extraction Prompt: overall instructions telling the LLM how to approach the extraction.
  • Variables to Extract: a list of variables, each with a name, a data type (string, number, boolean), and a per-variable hint describing what to capture.
For example:
Each extracted value is stored in gathered_context. It is not available in any nodeā€™s Prompt - reference it in Webhook node payloads as {{gathered_context.variable_name}}, or read it from the run record after the call completes.

ā€‹
Using multiple Agent Nodes

Break complex conversations into phases. Each Agent Node handles one part of the flow. A debt collection workflow, for example, might chain three Agent Nodes: identity verification, offer presentation, and objection handling. Nodes pass context forward automatically, but not into prompts. Variables extracted in one node are stored in gathered_context and merged with variables from later nodes as the call progresses. gathered_context is not available in any nodeā€™s Prompt - it can only be referenced in Webhook node payloads and in the run record after the call completes. If a later Agent Node needs to react to something extracted earlier, that logic has to live in the promptā€™s own instructions, not in a {{gathered_context...}} reference.

ā€‹
Common mistakes

No outgoing edges. Every Agent Node needs at least one edge. A dead-end node has no exit path and will trap the call. Putting global instructions in the Agent prompt. Rules that apply across the entire workflow - persona, tone, compliance guardrails - belong in the Global Node, not repeated in every Agent Node. Vague edge conditions. The LLM picks the edge that best matches the conversation state. Overly broad conditions cause unpredictable routing between nodes.

ā€‹
Next Steps

End Call Node

Terminate the conversation with a closing message.

Global Node

Write shared instructions that apply to every node.

Context and Variables

Understand how gathered_context is built and where it can be referenced.

QA Node

Evaluate agent performance automatically after each call.